Upload complete model

README.md

@@ -10,7 +10,7 @@ library_name: mlx
 ### CURRENTLY UPLOADING
 ### CURRENTLY UPLOADING
 
-**See Kimi-K2-Thinking 4.25bit MLX in action - [demonstration video - coming soon](https://youtube.com/xcreate)**
+**See Kimi-K2-Thinking 4.25bit MLX in action - [demonstration video](https://youtu.be/GydlPnP7IYk)**
 
 *q4.25bit quant perplexity TBA, but q4.5bit quant typically achieves 1.168 perplexity in our testing*
 | Quantization | Perplexity |
@@ -30,7 +30,7 @@ library_name: mlx
 * Memory usage: MBP ~80GB + Mac Studio ~450GB
 * Expect ~22 tokens/s @ 1000 tokens
 * Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx) 0.29
-* For more details see [demonstration video - coming soon](https://youtube.com/xcreate) or visit [Kimi-K2-Thinking](https://huggingface.co/moonshotai/Kimi-K2-Thinking).
+* For more details see [demonstration video](https://youtu.be/GydlPnP7IYk) or visit [Kimi-K2-Thinking](https://huggingface.co/moonshotai/Kimi-K2-Thinking).
 
 ## Disclaimer